Unit name | Text Analytics |
---|---|
Unit code | COMSM0037 |
Credit points | 10 |
Level of study | M/7 |
Teaching block(s) |
Teaching Block 2 (weeks 13 - 24) |
Unit director | Dr. Simpson |
Open unit status | Not open |
Pre-requisites |
Software Development: Programming and Algorithms |
Co-requisites |
Introduction to Artificial Intelligence EMATM0044 |
School/department | Department of Computer Science |
Faculty | Faculty of Engineering |
The sheer volume and complexity of online natural-language text data means that traditional manual techniques and stand-alone applications are very often no longer sufficient to process and analyse this data and provide useful information. Furthermore, the availability of large-scale sources of text data, such as those found on social media websites, opens up new opportunities for estimating the sentiment or opinions of large groups of people.
This unit aims to provide students with a thorough grounding in the computational analysis of large-scale natural-language texts. The unit will cover methods for unsupervised and supervised text mining including text pre-processing, structured data extraction, clustering of documents, classification of documents, and sentiment analysis using different techniques. The methods taught include rule-based approaches, traditional machine learning techniques as well as more recent techniques such as those based on deep-learning neural networks.
Students will be able to
Teaching will be delivered through a combination of synchronous and asynchronous sessions, including lectures, practical activities and self-directed exercises.
80% coursework, 20% in-class tests